Installation

  1. Install R
  2. Install RTools if you are on Windows
  3. Install RStudio

For more details, see Software and Package Versions.

Running This Code

  1. Ensure the installation steps above are completed
  2. Download a zip of the code and data here and unzip it
  3. In RStudio, open the src/src.Rproj file
  4. Then, open the src/index.Rmd file
  5. In RStudio:
    • Run all code: Click the Run drop down (top right of the code pane) and click Run All
    • Generate HTML version: Click knit (top left of code pane) and a file will be generated in docs/index.html

Libraries

Install R packages if needed.

# Required packages
required_packages <- c(
    "rmarkdown",
    "bookdown",
    "knitr",
    "tidyverse",
    "purrr",
    "glue",
    "lubridate",
    "scales",
    "patchwork",
    "DiagrammeR",
    "DiagrammeRsvg",
    "webshot2",
    "magick",
    "rsvg",
    "sf",
    "tmap",
    "ggspatial",
    "prettymapr",
    "units",
    "boot"
)

# Try to install packages if not installed
default_options <- options()
tryCatch(
    {
        # Disable interactivity
        options(install.packages.compile.from.source = "always")
        
        # Install package if not installed
        for (package in required_packages) {
            is_package_installed <- require(package, character.only = TRUE)
            if (!is_package_installed) {
                cat(paste0("Installing package: ", package, "\n"))
                install.packages(package)
            } else {
                cat(paste0("Package already installed: ", package, "\n"))
            }
        }
    },
    error = function(cond) {
        stop(cond)
    },
    finally = {
        options(default_options) # reset interactivity
    }
)

Load R libraries.

library(boot)
library(DiagrammeR)
library(ggplot2)
library(ggspatial)
library(glue)
library(lubridate)
library(patchwork)
library(sf)
library(tidyverse)
library(tmap)

Data

Read data from the data folder.

ddesc <- read_csv("../data/data.csv")
ddesc

Vancouver Bikeways

Bikeways data with manually verified (Google Street View/Earth and Web Search) painted lanes and cycle tracks for Vancouver, Canada

# Read data
vancbike_raw <- read_sf("../data/vancouver-bikeways-2024-06-02.geojson")

# Get download date
vancbike_dldate <- ddesc %>% filter(
    file == "vancouver-bikeways-2024-06-02.geojson"
) %>% pull(download_date)

Map

Only the first 1000 records are shown.

tmap_mode("view")
tm_shape(vancbike_raw %>% head(1000)) +
    tm_lines(
        col = "#336699",
        border.col = "white",
        popup.vars = TRUE
    )

Data

  • Columns: 23
  • Rows: 3666
vancbike_raw %>% as_tibble

Dictionary

The data contains the following columns:

#vancbike_ddict <- read_csv("../data/vancouver-bikeways-2024-06-02-datadict.csv")
#vancbike_ddict

Details

print(vancbike_raw)
## Simple feature collection with 3666 features and 22 fields
## Geometry type: LINESTRING
## Dimension:     XY
## Bounding box:  xmin: -123.2238 ymin: 49.19899 xmax: -123.0233 ymax: 49.31428
## Geodetic CRS:  WGS 84
## # A tibble: 3,666 × 23
##    id     street     status road_type road_type_recode install_year install_type
##    <chr>  <chr>      <chr>  <chr>     <chr>                   <dbl> <chr>       
##  1 294725 Highbury   Active Resident… Local                    2006 Local Street
##  2 294726 Highbury   Active Resident… Local                    2006 Local Street
##  3 294731 W 8th Ave  Active Resident… Local                    1994 Local Street
##  4 294732 W 8th Ave  Active Resident… Local                    1994 Local Street
##  5 294733 Off Street Active Lane      Local                    2003 Protected B…
##  6 294736 W 5th Ave  Active Resident… Local                    2009 Local Street
##  7 294737 W 8th Ave  Active Resident… Local                    1994 Local Street
##  8 294738 W 7th Ave  Active Resident… Local                    1994 Local Street
##  9 294739 W 7th Ave  Active Resident… Local                    1994 Local Street
## 10 294742 W 7th Ave  Active Resident… Local                    1994 Local Street
## # ℹ 3,656 more rows
## # ℹ 16 more variables: verify_install_year <dbl>, verify_install_date <chr>,
## #   verify_install_type <chr>, verify_install_comment <chr>,
## #   verify_upgrade1_year <dbl>, verify_upgrade1_date <chr>,
## #   verify_upgrade1_type <chr>, verify_upgrade1_comment <chr>,
## #   verify_upgrade2_year <dbl>, verify_upgrade2_date <chr>,
## #   verify_upgrade2_type <chr>, verify_upgrade2_comment <chr>, …

Calgary Bikeways

Bikeways data with manually verified (Google Street View/Earth and Web Search) painted lanes and cycle tracks for Calgary, Canada

# Read data
calgbike_raw <- read_sf("../data/calgary-bikeways-2024-06-05.geojson")

# Get download date
calgbike_dldate <- ddesc %>% filter(
    file == "calgary-bikeways-2024-06-05.geojson"
) %>% pull(download_date)

Map

Only the first 1000 records are shown.

tmap_mode("view")
tm_shape(calgbike_raw %>% head(1000)) +
    tm_lines(
        col = "#336699",
        border.col = "white",
        popup.vars = TRUE
    )

Data

  • Columns: 22
  • Rows: 4169
calgbike_raw %>% as_tibble

Dictionary

The data contains the following columns:

#calgbike_ddict <- read_csv("../data/calgary-bikeways-2024-06-05-datadict.csv")
#calgbike_ddict

Details

print(calgbike_raw)
## Simple feature collection with 4169 features and 21 fields
## Geometry type: MULTILINESTRING
## Dimension:     XY
## Bounding box:  xmin: -114.269 ymin: 50.89762 xmax: -113.9302 ymax: 51.17778
## Geodetic CRS:  WGS 84
## # A tibble: 4,169 × 22
##    id    street status   road_type road_type_recode install_year install_type   
##    <chr> <chr>  <chr>    <chr>     <chr>                   <dbl> <chr>          
##  1 1     <NA>   EXISTING <NA>      <NA>                     2003 On-Street Bike…
##  2 2     <NA>   EXISTING <NA>      <NA>                     2009 On-Street Bike…
##  3 3     <NA>   EXISTING <NA>      <NA>                     2009 On-Street Bike…
##  4 4     <NA>   EXISTING <NA>      <NA>                     1999 On-Street Bike…
##  5 5     <NA>   EXISTING <NA>      <NA>                     1999 On-Street Bike…
##  6 6     <NA>   EXISTING <NA>      <NA>                     2005 On-Street Bike…
##  7 7     <NA>   EXISTING <NA>      <NA>                     1999 On-Street Bike…
##  8 8     <NA>   EXISTING <NA>      <NA>                     1999 On-Street Bike…
##  9 9     <NA>   EXISTING <NA>      <NA>                     1999 On-Street Bike…
## 10 10    <NA>   INACTIVE <NA>      <NA>                       NA DECOMMISSIONED 
## # ℹ 4,159 more rows
## # ℹ 15 more variables: verify_install_year <dbl>, verify_install_date <chr>,
## #   verify_install_type <chr>, verify_install_comment <chr>,
## #   verify_upgrade1_year <dbl>, verify_upgrade1_date <chr>,
## #   verify_upgrade1_type <chr>, verify_upgrade1_comment <chr>,
## #   verify_upgrade2_year <dbl>, verify_upgrade2_date <chr>,
## #   verify_upgrade2_type <chr>, verify_upgrade2_comment <chr>, …

Toronto Bikeways

Bikeways data with manually verified (Google Street View/Earth and Web Search) painted lanes and cycle tracks for Toronto, Canada

# Read data
toronbike_raw <- read_sf("../data/toronto-bikeways-2024-06-02.geojson")

# Get download date
toronbike_dldate <- ddesc %>% filter(
    file == "toronto-bikeways-2024-06-02.geojson"
) %>% pull(download_date)

Map

Only the first 1000 records are shown.

tmap_mode("view")
tm_shape(toronbike_raw %>% head(1000)) +
    tm_lines(
        col = "#336699",
        border.col = "white",
        popup.vars = TRUE
    )

Data

  • Columns: 23
  • Rows: 1323
toronbike_raw %>% as_tibble

Dictionary

The data contains the following columns:

#toronbike_ddict <- read_csv("../data/toronto-bikeways-2024-06-02-datadict.csv")
#toronbike_ddict

Details

print(toronbike_raw)
## Simple feature collection with 1323 features and 22 fields
## Geometry type: MULTILINESTRING
## Dimension:     XY
## Bounding box:  xmin: -79.63039 ymin: 43.58221 xmax: -79.11803 ymax: 43.85546
## Geodetic CRS:  WGS 84
## # A tibble: 1,323 × 23
##    id    street    street_from street_to road_type road_type_recode install_year
##    <chr> <chr>     <chr>       <chr>     <chr>     <chr>                   <dbl>
##  1 8     Bloor St… Parliament… Castle F… Major Ar… Arterial                 2001
##  2 17    Lake Sho… Humber Bay… Humber B… Major Ar… Arterial                 2001
##  3 18    Lake Sho… 37 M E Fle… Humber B… Major Ar… Arterial                 2001
##  4 19    Lake Sho… 50.7 M E L… 37 M E F… Major Ar… Arterial                 2001
##  5 38    Queens Q… Martin Goo… Bathurst… Collector Collector                2001
##  6 39    Davenpor… Cottingham… Macphers… Minor Ar… Arterial                 2001
##  7 40    Elizabet… College St  Gerrard … Collector Collector                2001
##  8 41    Gerrard … Yonge St    Church St Minor Ar… Arterial                 2001
##  9 42    Macphers… Davenport … Poplar P… Collector Collector                2001
## 10 43    Lake Sho… Marine Par… Palace P… Major Ar… Arterial                 2001
## # ℹ 1,313 more rows
## # ℹ 16 more variables: install_type <chr>, verify_install_year <dbl>,
## #   verify_install_date <chr>, verify_install_type <chr>,
## #   verify_install_comment <chr>, verify_upgrade1_year <dbl>,
## #   verify_upgrade1_date <chr>, verify_upgrade1_type <chr>,
## #   verify_upgrade1_comment <chr>, verify_upgrade2_year <dbl>,
## #   verify_upgrade2_date <chr>, verify_upgrade2_type <chr>, …

Toronto KSI

KSI (2006-2022) data from the Toronto Police Service (TPS) Public Safety Data Portal for Toronto, Ontario

# Read data
ksi_raw <- read_sf("../data/toronto-ksi-2024-06-01.geojson")

# Get download date
ksi_dldate <- ddesc %>% filter(
    file == "toronto-ksi-2024-06-01.geojson"
) %>% pull(download_date)

Map

Note: Due to the large number of records, only the latest year of 2023 is displayed (n = 695).

tmap_mode("view")
tm_shape(ksi_raw %>% filter(year(DATE) == max(year(DATE)))) +
    tm_dots(
        col = "ACCLASS",
        clustering = TRUE,
        popup.vars = TRUE
    )

Data

  • Columns: 53
  • Rows: 18957
ksi_raw %>% as_tibble()

Dictionary

The data contains the following columns:

ksi_ddict <- read_csv("../data/toronto-ksi-2024-06-01-datadict.csv")
ksi_ddict

Details

print(ksi_raw)
## Simple feature collection with 18957 features and 52 fields
## Geometry type: POINT
## Dimension:     XY
## Bounding box:  xmin: -79.63839 ymin: 43.58968 xmax: -79.12297 ymax: 43.85545
## Geodetic CRS:  WGS 84
## # A tibble: 18,957 × 53
##    OBJECTID INDEX_  ACCNUM DATE                TIME  STREET1      STREET2 OFFSET
##       <int> <chr>   <chr>  <dttm>              <chr> <chr>        <chr>   <chr> 
##  1        1 3389067 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  2        2 3389068 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  3        3 3389069 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  4        4 3389070 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  5        5 3389071 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  6        6 3389072 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  7        7 3389073 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  8        8 3389074 893184 2006-01-01 05:00:00 236   WOODBINE AVE O CONN… <NA>  
##  9        9 3433023 909646 2006-01-01 05:00:00 315   DANFORTH AVE WEST L… <NA>  
## 10       10 3433024 909646 2006-01-01 05:00:00 315   DANFORTH AVE WEST L… <NA>  
## # ℹ 18,947 more rows
## # ℹ 45 more variables: ROAD_CLASS <chr>, DISTRICT <chr>, LATITUDE <dbl>,
## #   LONGITUDE <dbl>, ACCLOC <chr>, TRAFFCTL <chr>, VISIBILITY <chr>,
## #   LIGHT <chr>, RDSFCOND <chr>, ACCLASS <chr>, IMPACTYPE <chr>, INVTYPE <chr>,
## #   INVAGE <chr>, INJURY <chr>, FATAL_NO <int>, INITDIR <chr>, VEHTYPE <chr>,
## #   MANOEUVER <chr>, DRIVACT <chr>, DRIVCOND <chr>, PEDTYPE <chr>,
## #   PEDACT <chr>, PEDCOND <chr>, CYCLISTYPE <chr>, CYCACT <chr>, …

Files

The data files are available below:

Cleaning

Determine Temporal Scale

parsed <- list()
msg <- list()
bikeways <-  list(
    Vancouver = vancbike_raw,
    Calgary = calgbike_raw,
    Toronto = toronbike_raw
)

for (city in names(bikeways)) {
    
    # Filter for verified bikeways only
    df <- bikeways[[city]] %>%
        filter(
            !is.na(verify_install_year) |
            !is.na(verify_upgrade1_year) |
            !is.na(verify_upgrade2_year)
        )
    
    # Filter out non verified
    if (city == "Vancouver") {
        df <- df %>%
            filter(is.na(no_verify_install_type))
    }
    
    # Try to parse install dates
    df <- df %>%
        as_tibble %>%
        mutate(
            clean_date = str_to_lower(
                str_replace_all(
                    verify_install_date,
                    "[^[:alnum:]]",
                    " "
                )
            ),
            parsed_date = ymd(clean_date) %>%
                coalesce(ydm(clean_date)) %>%
                coalesce(mdy(clean_date)) %>%
                coalesce(myd(clean_date)) %>%
                coalesce(dmy(clean_date)) %>%
                coalesce(dym(clean_date)),
            parsed_month = if_else(
                !str_starts(str_trim(clean_date), "pre") & is.na(parsed_date),
                yq(clean_date) %>%
                coalesce(ym(clean_date)) %>%
                coalesce(my(clean_date)),
                NA
            )
        ) %>%
        rename(
            clean_install_date = clean_date,
            parsed_install_date = parsed_date,
            parsed_install_month = parsed_month
        )
    
    # Try to parse upgrade 1 dates
    df <- df %>%
        as_tibble %>%
        mutate(
            clean_date = str_to_lower(
                str_replace_all(
                    verify_upgrade1_date,
                    "[^[:alnum:]]",
                    " "
                )
            ),
            parsed_date = ymd(clean_date) %>%
                coalesce(ydm(clean_date)) %>%
                coalesce(mdy(clean_date)) %>%
                coalesce(myd(clean_date)) %>%
                coalesce(dmy(clean_date)) %>%
                coalesce(dym(clean_date)),
            parsed_month = if_else(
                !str_starts(str_trim(clean_date), "pre") & is.na(parsed_date),
                yq(clean_date) %>%
                coalesce(ym(clean_date)) %>%
                coalesce(my(clean_date)),
                NA
            )
        ) %>%
        rename(
            clean_upgrade1_date = clean_date,
            parsed_upgrade1_date = parsed_date,
            parsed_upgrade1_month = parsed_month
        )
    
    # Try to parse upgrade 1 dates
    df <- df %>%
        as_tibble %>%
        mutate(
            clean_date = str_to_lower(
                str_replace_all(
                    verify_upgrade2_date,
                    "[^[:alnum:]]",
                    " "
                )
            ),
            parsed_date = ymd(clean_date) %>%
                coalesce(ydm(clean_date)) %>%
                coalesce(mdy(clean_date)) %>%
                coalesce(myd(clean_date)) %>%
                coalesce(dmy(clean_date)) %>%
                coalesce(dym(clean_date)),
            parsed_month = if_else(
                !str_starts(str_trim(clean_date), "pre") & is.na(parsed_date),
                yq(clean_date) %>%
                coalesce(ym(clean_date)) %>%
                coalesce(my(clean_date)),
                NA
            )
        ) %>%
        rename(
            clean_upgrade2_date = clean_date,
            parsed_upgrade2_date = parsed_date,
            parsed_upgrade2_month = parsed_month
        )
    
    # Num of records with install or upgrade dates
    n_idates <- df %>% filter(!is.na(verify_install_date)) %>% nrow
    n_u1dates <- df %>% filter(!is.na(verify_upgrade1_date)) %>% nrow
    n_u2dates <- df %>% filter(!is.na(verify_upgrade2_date)) %>% nrow
    
    # Num of records with parsed dates and months
    n_pidates <- df %>% filter(!is.na(parsed_install_date)) %>% nrow
    n_pimonths <- df %>% filter(!is.na(parsed_install_month)) %>% nrow
    n_pu1dates <- df %>% filter(!is.na(parsed_upgrade1_date)) %>% nrow
    n_pu1months <- df %>% filter(!is.na(parsed_upgrade1_month)) %>% nrow
    n_pu2dates <- df %>% filter(!is.na(parsed_upgrade2_date)) %>% nrow
    n_pu2months <- df %>% filter(!is.na(parsed_upgrade2_month)) %>% nrow
    
    # Perc of records with install or upgrade dates
    perc_idates <- round(n_idates / nrow(df) * 100, 2)
    perc_u1dates <- round(n_u1dates / nrow(df) * 100, 2)
    perc_u2dates <- round(n_u2dates / nrow(df) * 100, 2)
    
    # Perc of records with parsed dates and months
    perc_pidates <- round(n_pidates / nrow(df) * 100, 2)
    perc_pimonths <- round(n_pimonths / nrow(df) * 100, 2)
    perc_pu1dates <- round(n_pu1dates / nrow(df) * 100, 2)
    perc_pu1months <- round(n_pu1months / nrow(df) * 100, 2)
    perc_pu2dates <- round(n_pu2dates / nrow(df) * 100, 2)
    perc_pu2months <- round(n_pu2months / nrow(df) * 100, 2)
    
    # Add to list
    msg[[city]] <- glue(
        "\n\n**Verified {city} Bikeways (n = {df %>% nrow}, 100%)**\n",
        "\n* Install Dates: {n_idates} ({perc_idates}%)",
        "\n\t* Parsable Dates: {n_pidates} ({perc_pidates}%)",
        "\n \t* Parsable Months: {n_pimonths} ({perc_pimonths}%)",
        "\n* Upgrade 1 Dates: {n_u1dates} ({perc_u1dates}%)",
        "\n\t* Parsable Dates: {n_pu1dates} ({perc_pu1dates}%)",
        "\n\t* Parsable Months: {n_pu1months} ({perc_pu1months}%)",
        "\n* Upgrade 2 Dates: {n_u2dates} ({perc_u2dates}%)",
        "\n\t* Parsable Dates: {n_pu2dates} ({perc_pu2dates}%)",
        "\n\t* Parsable Months: {n_pu2months} ({perc_pu2months}%)\n\n"
    )
    
    df <- df %>% filter(
        !is.na(verify_install_date) |
        !is.na(verify_upgrade1_date) |
        !is.na(verify_upgrade2_date)
    )
    parsed[[city]] <- data.frame(
        orig_date = c(df$verify_install_date, df$verify_upgrade1_date, df$verify_upgrade2_date),
        clean_date = c(df$clean_install_date, df$clean_upgrade1_date, df$clean_upgrade2_date),
        parsed_date = c(df$parsed_install_date, df$parsed_upgrade1_date, df$parsed_upgrade2_date),
        parsed_month = c(df$parsed_install_month, df$parsed_upgrade1_month, df$parsed_upgrade2_month)
    )
    
    parsed[[city]] <- parsed[[city]] %>%
        group_by(orig_date) %>%
        count() %>%
        ungroup %>%
        left_join(
             parsed[[city]] %>%
                distinct(orig_date, .keep_all = T),
             by = "orig_date"
        ) %>%
        arrange(desc(n)) %>%
        filter(!is.na(orig_date))
}
cat(msg[["Vancouver"]])

Verified Vancouver Bikeways (n = 745, 100%)

  • Install Dates: 532 (71.41%)
    • Parsable Dates: 137 (18.39%)
    • Parsable Months: 96 (12.89%)
  • Upgrade 1 Dates: 264 (35.44%)
    • Parsable Dates: 55 (7.38%)
    • Parsable Months: 151 (20.27%)
  • Upgrade 2 Dates: 8 (1.07%)
    • Parsable Dates: 0 (0%)
    • Parsable Months: 7 (0.94%)
parsed[["Vancouver"]]
cat(msg[["Calgary"]])

Verified Calgary Bikeways (n = 766, 100%)

  • Install Dates: 530 (69.19%)
    • Parsable Dates: 367 (47.91%)
    • Parsable Months: 29 (3.79%)
  • Upgrade 1 Dates: 35 (4.57%)
    • Parsable Dates: 15 (1.96%)
    • Parsable Months: 8 (1.04%)
  • Upgrade 2 Dates: 8 (1.04%)
    • Parsable Dates: 0 (0%)
    • Parsable Months: 8 (1.04%)
parsed[["Calgary"]]
cat(msg[["Toronto"]])

Verified Toronto Bikeways (n = 326, 100%)

  • Install Dates: 284 (87.12%)
    • Parsable Dates: 163 (50%)
    • Parsable Months: 5 (1.53%)
  • Upgrade 1 Dates: 58 (17.79%)
    • Parsable Dates: 39 (11.96%)
    • Parsable Months: 2 (0.61%)
  • Upgrade 2 Dates: 4 (1.23%)
    • Parsable Dates: 1 (0.31%)
    • Parsable Months: 0 (0%)
parsed[["Toronto"]]